Localizing Anatomical Landmarks in Ocular Images Using Zoom-In Attentive Networks

Localizing Anatomical Landmarks in Ocular Images Using Zoom-In Attentive Networks

Ophthalmic Medical Image Analysis (Lecture Notes in Computer Science)

10.1007/978-3-031-16525-2_10

http://dx.doi.org/10.1007/978-3-031-16525-2_10

Xiaofeng Lei, Shaohua Li, Xinxing Xu, Huazhu Fu, Yong Liu, Yih-Chung Tham, Yangqin Feng, Mingrui Tan, Yanyu Xu, Jocelyn Hui Lin Goh, Rick Siow Mong Goh, Ching-Yu Cheng

14 September 2022

Lei, X., Li, S., Xu, X., Fu, H., Liu, Y., Tham, Y.-C., Feng, Y., Tan, M., Xu, Y., Goh, J. H. L., Goh, R. S. M., & Cheng, C.-Y. (2022). Localizing Anatomical Landmarks in Ocular Images Using Zoom-In Attentive Networks. Lecture Notes in Computer Science, 94–104. https://doi.org/10.1007/978-3-031-16525-2_10

Localizing anatomical landmarks are important tasks in medical image analysis. However, the landmarks to be localized often lack prominent visual features. Their locations are elusive and easily confused with the background, and thus precise localization highly depends on the context formed by their surrounding areas. In addition, the required precision is usually higher than segmentation and object detection tasks. Therefore, localization has its unique challenges different from segmentation or detection. In this paper, we propose a zoom-in attentive network (ZIAN) for anatomical landmark localization in ocular images. First, a coarse-to-fine, or “zoom-in” strategy is utilized to learn the contextualized features in different scales. Then, an attentive fusion module is adopted to aggregate multi-scale features, which consists of 1) a co-attention network with a multiple regions-of-interest (ROIs) scheme that learns complementary features from the multiple ROIs, 2) an attention-based fusion module which integrates the multi-ROIs features and non-ROI features. We evaluated ZIAN on two open challenge tasks, i.e., the fovea localization in fundus images and scleral spur localization in AS-OCT images. Experiments show that ZIAN achieves promising performances and outperforms state-of-the-art localization methods. The source code and trained models of ZIAN are available at https://github.com/leixiaofeng-astar/OMIA9-ZIAN.

Publisher Copyright

This research / project is supported by the A*STAR - AME Programmatic Funds
Grant Reference no. : A20H4b0141

This research / project is supported by the A*STAR - RIE2020 Health and Biomedical Sciences (HBMS) Industry Alignment Fund Pre-Positioning
Grant Reference no. : H20c6a0031

This research / project is supported by the A*STAR - Career Development Fund
Grant Reference no. : C210112016

This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-16525-2_10

https://oar.a-star.edu.sg/communities-collections/articles/18860

9783031165252

9783031165245

Institute of High Performance Computing